Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    references to the word "serpent" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    zoom
    -0.17
     sinon
    -0.17
    ritz
    -0.16
    lear
    -0.15
    uteur
    -0.15
    ÛĮدÛĮ
    -0.15
    893
    -0.14
    =nil
    -0.14
    boom
    -0.14
    beat
    -0.14
    POSITIVE LOGITS
    enity
    0.23
     ser
    0.22
    gio
    0.22
     Ser
    0.22
    pent
    0.21
    mons
    0.20
     SER
    0.20
    -ser
    0.20
    (serializers
    0.19
    enade
    0.19
    Act Density 0.015%

    No Known Activations